On the Complexity of Solving Markov Decision Problems
This is an incremental review for AI researchers in planning and reinforcement learning, highlighting gaps in practical MDP solutions.
The paper tackles the complexity of solving Markov decision problems (MDPs), summarizing theoretical efficiency and practical challenges, and argues that more study is needed to develop fast algorithms for large-scale problems.
Markov decision problems (MDPs) provide the foundations for a number of problems of interest to AI researchers studying automated planning and reinforcement learning. In this paper, we summarize results regarding the complexity of solving MDPs and the running time of MDP solution algorithms. We argue that, although MDPs can be solved efficiently in theory, more study is needed to reveal practical algorithms for solving large problems quickly. To encourage future research, we sketch some alternative methods of analysis that rely on the structure of MDPs.